Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5190 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1273815 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1507. Min Act: -0.0001

Data Index: 207022 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1084094 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1465. Min Act: -0.0001

Data Index: 1230733 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1176157 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1384. Min Act: -0.0001

Data Index: 589431 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1378. Min Act: -0.0001

Data Index: 1044571 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1399. Min Act: -0.0002

Data Index: 1184648 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1346. Min Act: -0.0001

Data Index: 586496 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1315. Min Act: -0.0001

Data Index: 631777 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1338. Min Act: -0.0001

Data Index: 597574 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1292. Min Act: -0.0001

Data Index: 363206 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1304. Min Act: -0.0001

Data Index: 153075 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1253. Min Act: -0.0001

Data Index: 1327656 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1227. Min Act: -0.0001

Data Index: 698059 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1176. Min Act: -0.0001

Data Index: 810555 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1153. Min Act: -0.0001

Data Index: 686328 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1154. Min Act: -0.0001

Data Index: 833685 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1117. Min Act: -0.0001

Data Index: 1027234 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1359150 (C4 (Web Text))

Max Activating Token Index: 633